def train(self, samples, maxRuleSize=9999, mineOnlyClass=None):
"""Train with CPAR on the sample set, returning an AssociationRuleSet."""
self.MAX_RULE_SIZE = maxRuleSize
self.objPNData = PNData(samples)
self.lstRules = []
classes = self.objPNData.getClassList()
log("Dataset has %d classes over %d samples." %
(len(classes), len(samples)))
for current_class in classes:
if mineOnlyClass != None:
if current_class != mineOnlyClass:
continue
log("Processing class %s" % (current_class))
self.objPNData.setCurrentClass(current_class)
dblMinTotalWeight = self.dblTotalWeightFactor * self.objPNData.getTotalWeight(
)
lstAntecedent = []
while self.objPNData.getTotalWeight() > dblMinTotalWeight:
self.objPNData.refreshPNAData()
if self.objPNData.noValidGainsinPNarray(
self.dblMinGainThreshold):
#log("NO VALID GAINS....Breaking!");
break
#log('BEGIN DEPTH FIRST SEARCH - total weight %f > %f'%(self.objPNData.getTotalWeight(),dblMinTotalWeight))
self._CPARdfs(self.objPNData.copyPrimes(), lstAntecedent,
[current_class])
trules = len(self.lstRules)
self.removeDuplicateRules()
#log("End of rule search. Found %d rules total, %d after duplicates removed."%(trules,len(self.lstRules)))
arset = AssociationRuleSet()
arset.extend(self.lstRules)
arset.set_target_accuracy("laplace")
return self.remap_index_to_feature(arset, samples)
